rtnetlink.c

linux 内核源代码

		goto errout_dev;

	if (tb[IFLA_BROADCAST] &&
	    nla_len(tb[IFLA_BROADCAST]) < dev->addr_len)
		goto errout_dev;

	err = do_setlink(dev, ifm, tb, ifname, 0);
errout_dev:
	dev_put(dev);
errout:
	return err;
}

static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct net *net = skb->sk->sk_net;
	const struct rtnl_link_ops *ops;
	struct net_device *dev;
	struct ifinfomsg *ifm;
	char ifname[IFNAMSIZ];
	struct nlattr *tb[IFLA_MAX+1];
	int err;

	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
	if (err < 0)
		return err;

	if (tb[IFLA_IFNAME])
		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);

	ifm = nlmsg_data(nlh);
	if (ifm->ifi_index > 0)
		dev = __dev_get_by_index(net, ifm->ifi_index);
	else if (tb[IFLA_IFNAME])
		dev = __dev_get_by_name(net, ifname);
	else
		return -EINVAL;

	if (!dev)
		return -ENODEV;

	ops = dev->rtnl_link_ops;
	if (!ops)
		return -EOPNOTSUPP;

	ops->dellink(dev);
	return 0;
}

struct net_device *rtnl_create_link(struct net *net, char *ifname,
		const struct rtnl_link_ops *ops, struct nlattr *tb[])
{
	int err;
	struct net_device *dev;

	err = -ENOMEM;
	dev = alloc_netdev(ops->priv_size, ifname, ops->setup);
	if (!dev)
		goto err;

	if (strchr(dev->name, '%')) {
		err = dev_alloc_name(dev, dev->name);
		if (err < 0)
			goto err_free;
	}

	dev->nd_net = net;
	dev->rtnl_link_ops = ops;

	if (tb[IFLA_MTU])
		dev->mtu = nla_get_u32(tb[IFLA_MTU]);
	if (tb[IFLA_ADDRESS])
		memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]),
				nla_len(tb[IFLA_ADDRESS]));
	if (tb[IFLA_BROADCAST])
		memcpy(dev->broadcast, nla_data(tb[IFLA_BROADCAST]),
				nla_len(tb[IFLA_BROADCAST]));
	if (tb[IFLA_TXQLEN])
		dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
	if (tb[IFLA_OPERSTATE])
		set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
	if (tb[IFLA_LINKMODE])
		dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);

	return dev;

err_free:
	free_netdev(dev);
err:
	return ERR_PTR(err);
}

static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct net *net = skb->sk->sk_net;
	const struct rtnl_link_ops *ops;
	struct net_device *dev;
	struct ifinfomsg *ifm;
	char kind[MODULE_NAME_LEN];
	char ifname[IFNAMSIZ];
	struct nlattr *tb[IFLA_MAX+1];
	struct nlattr *linkinfo[IFLA_INFO_MAX+1];
	int err;

#ifdef CONFIG_KMOD
replay:
#endif
	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
	if (err < 0)
		return err;

	if (tb[IFLA_IFNAME])
		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
	else
		ifname[0] = '\0';

	ifm = nlmsg_data(nlh);
	if (ifm->ifi_index > 0)
		dev = __dev_get_by_index(net, ifm->ifi_index);
	else if (ifname[0])
		dev = __dev_get_by_name(net, ifname);
	else
		dev = NULL;

	if (tb[IFLA_LINKINFO]) {
		err = nla_parse_nested(linkinfo, IFLA_INFO_MAX,
				       tb[IFLA_LINKINFO], ifla_info_policy);
		if (err < 0)
			return err;
	} else
		memset(linkinfo, 0, sizeof(linkinfo));

	if (linkinfo[IFLA_INFO_KIND]) {
		nla_strlcpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
		ops = rtnl_link_ops_get(kind);
	} else {
		kind[0] = '\0';
		ops = NULL;
	}

	if (1) {
		struct nlattr *attr[ops ? ops->maxtype + 1 : 0], **data = NULL;

		if (ops) {
			if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
				err = nla_parse_nested(attr, ops->maxtype,
						       linkinfo[IFLA_INFO_DATA],
						       ops->policy);
				if (err < 0)
					return err;
				data = attr;
			}
			if (ops->validate) {
				err = ops->validate(tb, data);
				if (err < 0)
					return err;
			}
		}

		if (dev) {
			int modified = 0;

			if (nlh->nlmsg_flags & NLM_F_EXCL)
				return -EEXIST;
			if (nlh->nlmsg_flags & NLM_F_REPLACE)
				return -EOPNOTSUPP;

			if (linkinfo[IFLA_INFO_DATA]) {
				if (!ops || ops != dev->rtnl_link_ops ||
				    !ops->changelink)
					return -EOPNOTSUPP;

				err = ops->changelink(dev, tb, data);
				if (err < 0)
					return err;
				modified = 1;
			}

			return do_setlink(dev, ifm, tb, ifname, modified);
		}

		if (!(nlh->nlmsg_flags & NLM_F_CREATE))
			return -ENODEV;

		if (ifm->ifi_index || ifm->ifi_flags || ifm->ifi_change)
			return -EOPNOTSUPP;
		if (tb[IFLA_MAP] || tb[IFLA_MASTER] || tb[IFLA_PROTINFO])
			return -EOPNOTSUPP;

		if (!ops) {
#ifdef CONFIG_KMOD
			if (kind[0]) {
				__rtnl_unlock();
				request_module("rtnl-link-%s", kind);
				rtnl_lock();
				ops = rtnl_link_ops_get(kind);
				if (ops)
					goto replay;
			}
#endif
			return -EOPNOTSUPP;
		}

		if (!ifname[0])
			snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);

		dev = rtnl_create_link(net, ifname, ops, tb);

		if (IS_ERR(dev))
			err = PTR_ERR(dev);
		else if (ops->newlink)
			err = ops->newlink(dev, tb, data);
		else
			err = register_netdevice(dev);

		if (err < 0 && !IS_ERR(dev))
			free_netdev(dev);
		return err;
	}
}

static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct net *net = skb->sk->sk_net;
	struct ifinfomsg *ifm;
	struct nlattr *tb[IFLA_MAX+1];
	struct net_device *dev = NULL;
	struct sk_buff *nskb;
	int err;

	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
	if (err < 0)
		return err;

	ifm = nlmsg_data(nlh);
	if (ifm->ifi_index > 0) {
		dev = dev_get_by_index(net, ifm->ifi_index);
		if (dev == NULL)
			return -ENODEV;
	} else
		return -EINVAL;

	nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL);
	if (nskb == NULL) {
		err = -ENOBUFS;
		goto errout;
	}

	err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid,
			       nlh->nlmsg_seq, 0, 0);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in if_nlmsg_size */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(nskb);
		goto errout;
	}
	err = rtnl_unicast(nskb, NETLINK_CB(skb).pid);
errout:
	dev_put(dev);

	return err;
}

static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
{
	int idx;
	int s_idx = cb->family;

	if (s_idx == 0)
		s_idx = 1;
	for (idx=1; idx<NPROTO; idx++) {
		int type = cb->nlh->nlmsg_type-RTM_BASE;
		if (idx < s_idx || idx == PF_PACKET)
			continue;
		if (rtnl_msg_handlers[idx] == NULL ||
		    rtnl_msg_handlers[idx][type].dumpit == NULL)
			continue;
		if (idx > s_idx)
			memset(&cb->args[0], 0, sizeof(cb->args));
		if (rtnl_msg_handlers[idx][type].dumpit(skb, cb))
			break;
	}
	cb->family = idx;

	return skb->len;
}

void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
{
	struct sk_buff *skb;
	int err = -ENOBUFS;

	skb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL);
	if (skb == NULL)
		goto errout;

	err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in if_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
	err = rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_KERNEL);
errout:
	if (err < 0)
		rtnl_set_sk_err(RTNLGRP_LINK, err);
}

/* Protected by RTNL sempahore.  */
static struct rtattr **rta_buf;
static int rtattr_max;

/* Process one rtnetlink message. */

static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
	rtnl_doit_func doit;
	int sz_idx, kind;
	int min_len;
	int family;
	int type;
	int err;

	type = nlh->nlmsg_type;
	if (type > RTM_MAX)
		return -EOPNOTSUPP;

	type -= RTM_BASE;

	/* All the messages must have at least 1 byte length */
	if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct rtgenmsg)))
		return 0;

	family = ((struct rtgenmsg*)NLMSG_DATA(nlh))->rtgen_family;
	if (family >= NPROTO)
		return -EAFNOSUPPORT;

	sz_idx = type>>2;
	kind = type&3;

	if (kind != 2 && security_netlink_recv(skb, CAP_NET_ADMIN))
		return -EPERM;

	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
		rtnl_dumpit_func dumpit;

		dumpit = rtnl_get_dumpit(family, type);
		if (dumpit == NULL)
			return -EOPNOTSUPP;

		__rtnl_unlock();
		err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL);
		rtnl_lock();
		return err;
	}

	memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *)));

	min_len = rtm_min[sz_idx];
	if (nlh->nlmsg_len < min_len)
		return -EINVAL;

	if (nlh->nlmsg_len > min_len) {
		int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len);
		struct rtattr *attr = (void*)nlh + NLMSG_ALIGN(min_len);

		while (RTA_OK(attr, attrlen)) {
			unsigned flavor = attr->rta_type;
			if (flavor) {
				if (flavor > rta_max[sz_idx])
					return -EINVAL;
				rta_buf[flavor-1] = attr;
			}
			attr = RTA_NEXT(attr, attrlen);
		}
	}

	doit = rtnl_get_doit(family, type);
	if (doit == NULL)
		return -EOPNOTSUPP;

	return doit(skb, nlh, (void *)&rta_buf[0]);
}

static void rtnetlink_rcv(struct sk_buff *skb)
{
	rtnl_lock();
	netlink_rcv_skb(skb, &rtnetlink_rcv_msg);
	rtnl_unlock();
}

static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct net_device *dev = ptr;

	if (dev->nd_net != &init_net)
		return NOTIFY_DONE;

	switch (event) {
	case NETDEV_UNREGISTER:
		rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
		break;
	case NETDEV_REGISTER:
		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
		break;
	case NETDEV_UP:
	case NETDEV_DOWN:
		rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
		break;
	case NETDEV_CHANGE:
	case NETDEV_GOING_DOWN:
		break;
	default:
		rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
		break;
	}
	return NOTIFY_DONE;
}

static struct notifier_block rtnetlink_dev_notifier = {
	.notifier_call	= rtnetlink_event,
};

void __init rtnetlink_init(void)
{
	int i;

	rtattr_max = 0;
	for (i = 0; i < ARRAY_SIZE(rta_max); i++)
		if (rta_max[i] > rtattr_max)
			rtattr_max = rta_max[i];
	rta_buf = kmalloc(rtattr_max * sizeof(struct rtattr *), GFP_KERNEL);
	if (!rta_buf)
		panic("rtnetlink_init: cannot allocate rta_buf\n");

	rtnl = netlink_kernel_create(&init_net, NETLINK_ROUTE, RTNLGRP_MAX,
				     rtnetlink_rcv, &rtnl_mutex, THIS_MODULE);
	if (rtnl == NULL)
		panic("rtnetlink_init: cannot initialize rtnetlink\n");
	netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV);
	register_netdevice_notifier(&rtnetlink_dev_notifier);

	rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, rtnl_dump_ifinfo);
	rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL);
	rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL);
	rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL);

	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all);
	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all);
}

EXPORT_SYMBOL(__rta_fill);
EXPORT_SYMBOL(rtattr_strlcpy);
EXPORT_SYMBOL(rtattr_parse);
EXPORT_SYMBOL(__rtattr_parse_nested_compat);
EXPORT_SYMBOL(rtnetlink_put_metrics);
EXPORT_SYMBOL(rtnl_lock);
EXPORT_SYMBOL(rtnl_trylock);
EXPORT_SYMBOL(rtnl_unlock);
EXPORT_SYMBOL(rtnl_unicast);
EXPORT_SYMBOL(rtnl_notify);
EXPORT_SYMBOL(rtnl_set_sk_err);
EXPORT_SYMBOL(rtnl_create_link);
EXPORT_SYMBOL(ifla_policy);